Fast classification of engineering surfaces without surface parameters

A fast, new classification system for engineering surfaces has been developed and used to detect the incidence of wear. The novel feature of this system is that the classification can be performed without the need for any surface parameters. In addition, only normal working conditions data (the target class) are required to train a classifier. In this system, first, a surface to be classified is represented by a set of dissimilarity measures (e.g. differences in surface height) calculated between the unclassified surface and already pre-classified surfaces belonging to the target class. The representation set of measures is then used to assign a surface into the target class or reject as an outlier. Outliers are anomalies or faulty conditions that can be ill-defined, undersampled data or even unknown data. However, several problems still remain to be solved before the approach can be used as a fully functioning pattern recognition system for the applications in machine condition monitoring. This includes difficulties associated with selecting a right size of the representation set and building an accurate one-class classifier. These problems have been addressed in this study and analysis results for unworn and worn surfaces have been also presented. It was found that (i) skewness, correlation, principle component analysis dimensionality and boundary descriptor are well suited for selecting the representation set and (ii) a combiner of the Parzen and support vector data description (SVDD) classifiers with the median rule gives better classification results than single classifiers (i.e. Gaussian density, mixture of Gaussian densities, Parzen density and SVDD classifiers).

[1]  Robert P. W. Duin,et al.  Support vector domain description , 1999, Pattern Recognit. Lett..

[2]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[4]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[5]  Pawel Podsiadlo,et al.  Development of advanced quantitative analysis methods for wear particle characterization and classification to aid tribological system diagnosis , 2005 .

[6]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[7]  Klaus-Robert Müller,et al.  A consistency-based model selection for one-class classification , 2004, ICPR 2004.

[8]  Zhu Mian,et al.  Connectivity oriented fast Hough transform for tool wear monitoring , 2004, Pattern Recognit..

[9]  Hyun Joon Shin,et al.  One-class support vector machines - an application in machine fault detection and classification , 2005, Comput. Ind. Eng..

[10]  B. J. Roylance,et al.  Ferrography—then and now , 2005 .

[11]  H. Van Brussel,et al.  Machine Condition Monitoring Using Signal Classification Techniques , 2003 .

[12]  Sameer Singh,et al.  Novelty detection: a review - part 2: : neural network based approaches , 2003, Signal Process..

[13]  Malik Yousef,et al.  One-Class SVMs for Document Classification , 2002, J. Mach. Learn. Res..

[14]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[15]  Pawel Podsiadlo,et al.  Fractal-wavelet based classification of tribological surfaces , 2003 .

[16]  Robert P. W. Duin,et al.  Object Representation, Sample Size, and Data Set Complexity , 2006 .

[17]  G. Stachowiak,et al.  The Effects of Particle Characteristics on Three-Body Abrasive Wear , 2001 .

[18]  Robert P. W. Duin,et al.  Prototype selection for dissimilarity-based classifiers , 2006, Pattern Recognit..

[19]  Gwidon Stachowiak,et al.  Scale-invariant analysis of tribological surfaces , 2000 .

[20]  Don R. Hush,et al.  A Classification Framework for Anomaly Detection , 2005, J. Mach. Learn. Res..

[21]  Robert P. W. Duin,et al.  Support Vector Data Description , 2004, Machine Learning.

[22]  Robert P. W. Duin,et al.  Combining One-Class Classifiers , 2001, Multiple Classifier Systems.

[23]  M. J. Desforges,et al.  Applications of probability density estimation to the detection of abnormal conditions in engineering , 1998 .